Interspeech 2021
979 papers
Top Research Directions
Research directions most represented by Interspeech 2021 papers.
Top Authors
Impactful Papers
Papers from Interspeech 2021 that shaped research clusters.
Foundational
Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR
foundational
Metrics for Evaluating Code Switched Spe
MUCS 2021: Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages
foundational
Metrics for Evaluating Code Switched Spe
WeNet: Production Oriented Streaming and Non-Streaming End-to-End Speech Recognition Toolkit
foundational
Dynamic Chunk Training for Flexible Late
Flexi-Transducer: Optimizing Latency, Accuracy and Compute for Multi-Domain On-Device Scenarios
foundational
Dynamic Chunk Training for Flexible Late
Lightweight Causal Transformer with Local Self-Attention for Real-Time Speech Enhancement
foundational
Local Windowed Attention for Audio Trans
Enriching Source Style Transfer in Recognition-Synthesis Based Non-Parallel Voice Conversion
foundational
Adversarial Disentanglement of Speaker I
Ctrl-P: Temporal Control of Prosodic Variation for Speech Synthesis
foundational
Explicit Acoustic Feature Conditioning f
Keyword Transformer: A Self-Attention Model for Keyword Spotting
foundational
Processing Audio Spectrograms as Sequenc
NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
foundational
Audio Generation via Iterative Noise Ref
Influential
Application for Detecting Depression, Parkinson’s Disease and Dysphonic Speech
influential
Stratified and Nested Cross Validation f
Automatic Speech Recognition of Disordered Speech: Personalized Models Outperforming Human Listeners
influential
Speaker Adaptation for Personalized Spee
TVQVC: Transformer Based Vector Quantized Variational Autoencoder with CTC Loss for Voice Conversion
influential
Alignment Free Sequence Training with Co
LT-LM: A Novel Non-Autoregressive Language Model for Single-Shot Lattice Rescoring
influential
Laplacian Positional Encodings for Graph
Mixture Model Attention: Flexible Streaming and Non-Streaming Automatic Speech Recognition
influential
Unified Streaming and Non-Streaming Spee
WeNet: Production Oriented Streaming and Non-Streaming End-to-End Speech Recognition Toolkit
influential
Unified Streaming and Non-Streaming Spee
Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain
influential
Neural Speech Processing with Variable S
Towards Multi-Scale Style Control for Expressive Speech Synthesis
influential
Decomposing Speech Prosody Across Multip
Papers
« prev Page 20/20